Google Drive
Last updated
Last updated
Google Drive is a cloud storage and file synchronization service. This module provides functionality to load and process files from Google Drive, supporting various file formats and Google Workspace documents.
This module provides a sophisticated Google Drive document loader that can:
Load multiple file types
Process Google Workspace documents
Handle folder-based loading
Support shared drives
Process files recursively
Customize file type filtering
Handle OAuth2 authentication
Select Files or Folder ID: Choose specific files or provide a folder ID
File Types: Types of files to load:
Google Docs
Google Sheets
Google Slides
PDF Files
Text Files
Word Documents
PowerPoint
Excel Files
Include Subfolders: Process files in subfolders
Include Shared Drives: Access files from shared drives
Max Files: Maximum number of files to load (default: 50)
Text Splitter: A text splitter to process the extracted content
Additional Metadata: JSON object with additional metadata
Omit Metadata Keys: Comma-separated list of metadata keys to omit
Document: Array of document objects containing metadata and pageContent
Text: Concatenated string from pageContent of documents
Google Docs (application/vnd.google-apps.document)
Google Sheets (application/vnd.google-apps.spreadsheet)
Google Slides (application/vnd.google-apps.presentation)
Word (.docx)
Excel (.xlsx)
PowerPoint (.pptx)
PDF (.pdf)
Text Files (.txt)
OAuth2 authentication
Multiple file type support
Folder processing
Shared drive access
File type filtering
Text splitting support
Metadata customization
Error handling
Direct file selection
Multiple file support
File type filtering
Metadata preservation
Recursive folder processing
Subfolder support
File type filtering
Batch processing
Each document contains:
pageContent: Extracted content from the file
metadata:
fileName: Original file name
fileType: MIME type
fileId: Google Drive file ID
source: File path/URL
Additional custom metadata
Requires OAuth2 authentication
Handles rate limiting
Supports large files
Temporary file management
Memory-efficient processing
Error handling for invalid files
Automatic token refresh
Connect Credential: Google Drive OAuth2 credentials. Refer to